T5_Ru_VKR / README.md
Megnis's picture
End of training
a3592fc verified
metadata
license: apache-2.0
base_model: google-t5/t5-small
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: T5_Ru_VKR
    results: []

T5_Ru_VKR

This model is a fine-tuned version of google-t5/t5-small on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.8474
  • Rouge1: 0.0229
  • Rouge2: 0.0135
  • Rougel: 0.0228
  • Rougelsum: 0.0227
  • Gen Len: 18.845

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 4
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
No log 1.0 100 1.9287 0.0246 0.0135 0.0245 0.0242 18.865
No log 2.0 200 1.8761 0.0213 0.0135 0.0212 0.021 18.845
No log 3.0 300 1.8454 0.0213 0.0135 0.0212 0.021 18.845
No log 4.0 400 1.8474 0.0229 0.0135 0.0228 0.0227 18.845

Framework versions

  • Transformers 4.41.1
  • Pytorch 2.1.2
  • Datasets 2.18.0
  • Tokenizers 0.19.1